Model A

Anthropic

63.03/100

Supported · Public rank #48

90% interval 51.4–74.7

Claude Sonnet 4.6 vs GLM-5.2

Updated September 14, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B

GLM-5.2

Z.AI

68.19/100

Supported · Public rank #28

90% interval 61.7–74.7

Decision reading

GLM-5.2 has the higher public score estimate, 68.19 versus 63.03, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

8 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Share or export

Share on X LinkedInSocial card CSV JSON

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

Coding work
Code generation, repair, and software-engineering tasks
GLM-5.2
GLM-5.2 leads on the public coding lane, 61 to 52.2, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
GLM-5.2
GLM-5.2 leads on the public agentic lane, 58.5 to 44, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Long documents
Prompts that approach the documented context limit
GLM-5.2
GLM-5.2 has the larger documented context window.
Confidence: documented

Show secondary and unsupported calls

Chat turn cost
1K fresh input + 500 output tokens
GLM-5.2
GLM-5.2 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
GLM-5.2
GLM-5.2 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

18 Claude Sonnet 4.6 only

8 Shared

17 GLM-5.2 only

Shared results: 8
Claude Sonnet 4.6 only: 18
GLM-5.2 only: 17
Like-for-like categories: 3 / 8

1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Like-for-like

Claude Sonnet 4.6: 44.0; Supported · #93/153
GLM-5.2: 58.5; Supported · #29/153
Basis: BenchAlign lane · 9 vs 6 public rows
Reading: GLM-5.2 leads · intervals overlap

Coding

Like-for-like

Claude Sonnet 4.6: 52.2; Supported · #48/152
GLM-5.2: 61.0; Supported · #19/152
Basis: BenchAlign lane · 8 vs 8 public rows
Reading: GLM-5.2 leads · intervals overlap

Knowledge

Like-for-like

Claude Sonnet 4.6: 55.8; Supported · #51/183
GLM-5.2: 60.7; Supported · #35/183
Basis: BenchAlign lane · 6 vs 6 public rows
Reading: GLM-5.2 leads · intervals overlap

Instruction following

Directional only

Claude Sonnet 4.6: 48.2; #86/123
GLM-5.2: 89.8; #22/123
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Directional only

Reasoning

Not comparable

Claude Sonnet 4.6: 67.9; Unranked · 2 rankable rows
GLM-5.2: 74.8; Unranked · 2 rankable rows
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Math

Not comparable

Claude Sonnet 4.6: 49.0; Unranked · 2 rankable rows
GLM-5.2: 80.7; Unranked · 4 rankable rows
Basis: Provisional lane · 2 vs 2 weighted rows
Reading: Not comparable

Multilingual

Not comparable

Claude Sonnet 4.6: Not ranked
GLM-5.2: Not ranked
Basis: Provisional lane · 0 vs 0 weighted rows
Reading: Not comparable

Multimodal

Not comparable

Claude Sonnet 4.6: 54.1; #33/48
GLM-5.2: Not ranked
Basis: Provisional lane · 1 vs 0 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for Claude Sonnet 4.6 and GLM-5.2
Category	Claude Sonnet 4.6	GLM-5.2	Basis	Reading
Agentic	44.0Supported · #93/153	58.5Supported · #29/153	Like-for-likeBenchAlign lane · 9 vs 6 public rows	GLM-5.2 leads · intervals overlap
Coding	52.2Supported · #48/152	61.0Supported · #19/152	Like-for-likeBenchAlign lane · 8 vs 8 public rows	GLM-5.2 leads · intervals overlap
Knowledge	55.8Supported · #51/183	60.7Supported · #35/183	Like-for-likeBenchAlign lane · 6 vs 6 public rows	GLM-5.2 leads · intervals overlap
Instruction following	48.2#86/123	89.8#22/123	Directional onlyProvisional lane · 0 vs 0 weighted rows	Directional only
Reasoning	67.9Unranked · 2 rankable rows	74.8Unranked · 2 rankable rows	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Math	49.0Unranked · 2 rankable rows	80.7Unranked · 4 rankable rows	Not comparableProvisional lane · 2 vs 2 weighted rows	Not comparable
Multilingual	Not ranked	Not ranked	Not comparableProvisional lane · 0 vs 0 weighted rows	Not comparable
Multimodal	54.1#33/48	Not ranked	Not comparableProvisional lane · 1 vs 0 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

Terminal-Bench 2.0
Agentic
Claude Sonnet 4.6: 59.1%GLM-5.2: 81%Normalized gap 21.9Claude Sonnet 4.6 source GLM-5.2 source
LiveCodeBench (Vals)
Coding
Claude Sonnet 4.6: 82.1%GLM-5.2: 69.5%Normalized gap 12.6Claude Sonnet 4.6 source GLM-5.2 source
HLE
Knowledge
Claude Sonnet 4.6: 49%GLM-5.2: 54.7%Normalized gap 5.7Claude Sonnet 4.6 source GLM-5.2 source
GPQA
Knowledge
Claude Sonnet 4.6: 89.9%GLM-5.2: 91.2%Normalized gap 1.3Claude Sonnet 4.6 source GLM-5.2 source
MMLU-Pro (Vals)
Knowledge
Claude Sonnet 4.6: 87.3%GLM-5.2: 86.7%Normalized gap 0.6Claude Sonnet 4.6 source GLM-5.2 source

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Claude Sonnet 4.6: $0.0105; Fits in one request
GLM-5.2: $0.0036; Fits in one request

GLM-5.2 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Sonnet 4.6: $0.195; Fits in one request
GLM-5.2: $0.0832; Fits in one request

GLM-5.2 has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Claude Sonnet 4.6: $0.81; Does not fit in one request; Cached input priced at the published list-input rate
GLM-5.2: $0.352; Fits in one request; Cached input priced at the published list-input rate

Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate.

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

SpecificationClaude Sonnet 4.6GLM-5.2

Context window

Maximum documented context; output-token limits may be lower.

Claude Sonnet 4.6

200K

GLM-5.2

API model ID

Claude Sonnet 4.6

Not sourced

GLM-5.2

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Claude Sonnet 4.6

Not published

GLM-5.2

Not published

Documented inputs

Claude Sonnet 4.6

Not sourced

GLM-5.2

Not sourced

Documented outputs

Claude Sonnet 4.6

Not sourced

GLM-5.2

Not sourced

Provider availability

Claude Sonnet 4.6

Not sourced

GLM-5.2

Not sourced

Reasoning profile

Claude Sonnet 4.6

Non-Reasoning

GLM-5.2

Reasoning

Weight access

Claude Sonnet 4.6

Proprietary

GLM-5.2

Open Weight

License

Claude Sonnet 4.6

Proprietary

GLM-5.2

Open Weight

Release date

Claude Sonnet 4.6

2026-02-01

GLM-5.2

2026-06-16

If you already use one of these models

Deployment change: The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal: GLM-5.2 has the higher public score estimate, 68.19 versus 63.03, but the 90% score intervals overlap.
Workload cost: Repository review: $0.195 vs $0.0832. Cache-heavy agent loop: $0.81 vs $0.352.
Context tradeoff: GLM-5.2 has the larger documented window (1M).

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence43 rows

Agentic

Terminal-Bench 2.0
Claude Sonnet 4.659.1%
Source
GLM-5.281%
Source
GLM-5.2 leads this result
OSWorld-Verified
Claude Sonnet 4.672.1%
Source
GLM-5.2—
Not directly comparable
Claw-Eval
Claude Sonnet 4.667.8%
Source
GLM-5.2—
Not directly comparable
CyberGym
Claude Sonnet 4.665.2%
Source
GLM-5.2—
Not directly comparable
Gert Labs
Claude Sonnet 4.662.92%
Source
GLM-5.2—
Not directly comparable
OSWorld 2.0
Claude Sonnet 4.68.3%
Source
GLM-5.2—
Not directly comparable
JobBench
Claude Sonnet 4.636.9%
Source
GLM-5.2—
Not directly comparable
Terminal-Bench 2.1 (Vals)
Claude Sonnet 4.657.3%
Source
GLM-5.267.8%
Source
GLM-5.2 leads this result
ApprenticeBench
Claude Sonnet 4.62%
Source
GLM-5.2—
Not directly comparable
Terminal-Bench 3.0
Claude Sonnet 4.6—
GLM-5.24.6%
Source
Not directly comparable
MCP Atlas
Claude Sonnet 4.6—
GLM-5.276.8%
Source
Not directly comparable
Toolathlon
Claude Sonnet 4.6—
GLM-5.248.2%
Source
Not directly comparable
ResearchClawBench
Claude Sonnet 4.6—
GLM-5.220.7%
Source
Not directly comparable

Coding

SWE-bench Verified
Claude Sonnet 4.679.6%
Source
GLM-5.2—
Not directly comparable
SWE-Rebench
Claude Sonnet 4.660.7%
Source
GLM-5.2—
Not directly comparable
React Native Evals
Claude Sonnet 4.680.6%
Source
GLM-5.2—
Not directly comparable
Vibe Code Bench
Claude Sonnet 4.651.48%
Source
GLM-5.2—
Not directly comparable
cursorBench31
Claude Sonnet 4.648.8%
Source
GLM-5.2—
Not directly comparable
FrontierCode 1.1 Main
Claude Sonnet 4.624.3%
Source
GLM-5.2—
Not directly comparable
LiveCodeBench (Vals)
Claude Sonnet 4.682.1%
Source
GLM-5.269.5%
Source
Claude Sonnet 4.6 leads this result
SWE-bench (Vals)
Claude Sonnet 4.677.4%
Source
GLM-5.282.8%
Source
GLM-5.2 leads this result
SWE-bench Pro
Claude Sonnet 4.6—
GLM-5.262.1%
Source
Not directly comparable
NL2Repo
Claude Sonnet 4.6—
GLM-5.248.9%
Source
Not directly comparable
Terminal-Bench 2.0
Claude Sonnet 4.6—
GLM-5.281.0%
Source
Not directly comparable
ProgramBench
Claude Sonnet 4.6—
GLM-5.263.7%
Source
Not directly comparable
cursorBench32
Claude Sonnet 4.6—
GLM-5.255.0%
Source
Not directly comparable
OpenHarmony Bench
Claude Sonnet 4.6—
GLM-5.258.4%
Source
Not directly comparable

Reasoning

CritPt
Claude Sonnet 4.6—
GLM-5.220.9%
Source
Not directly comparable

Knowledge

GPQA
Claude Sonnet 4.689.9%
Source
GLM-5.291.2%
Source
GLM-5.2 leads this result
SuperGPQA
Claude Sonnet 4.695%
Source
GLM-5.2—
Not directly comparable
MMLU-Pro
Claude Sonnet 4.679.2%
Source
GLM-5.2—
Not directly comparable
HLE
Claude Sonnet 4.649%
Source
GLM-5.254.7%
Source
GLM-5.2 leads this result
GPQA Diamond (Vals)
Claude Sonnet 4.685.6%
Source
GLM-5.285.6%
Source
Tie
MMLU-Pro (Vals)
Claude Sonnet 4.687.3%
Source
GLM-5.286.7%
Source
Claude Sonnet 4.6 leads this result
GPQA-D
Claude Sonnet 4.6—
GLM-5.291.2%
Source
Not directly comparable
HLE w/o tools
Claude Sonnet 4.6—
GLM-5.240.5%
Source
Not directly comparable

Math

FrontierMath v2 (Tiers 1-3)
Claude Sonnet 4.632.400%
Source
GLM-5.2—
Not directly comparable
FrontierMath v2 (Tier 4)
Claude Sonnet 4.68.300%
Source
GLM-5.2—
Not directly comparable
AIME26
Claude Sonnet 4.6—
GLM-5.299.2%
Source
Not directly comparable
HMMT Nov 2025
Claude Sonnet 4.6—
GLM-5.294.4%
Source
Not directly comparable
HMMT Feb 2026
Claude Sonnet 4.6—
GLM-5.292.5%
Source
Not directly comparable
MMAnswerBench
Claude Sonnet 4.6—
GLM-5.291.0%
Source
Not directly comparable

Multimodal

CharXiv
Claude Sonnet 4.677.4%
Source
GLM-5.2—
Not directly comparable

Frequently asked questions

Which is better, Claude Sonnet 4.6 or GLM-5.2?

GLM-5.2 has the higher public score estimate, 68.19 versus 63.03, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Claude Sonnet 4.6 or GLM-5.2?

GLM-5.2 leads the public coding lane, 61 to 52.2, with Supported evidence for both models, although the 90% intervals overlap.

Which is better for agentic tasks, Claude Sonnet 4.6 or GLM-5.2?

GLM-5.2 leads the public agentic tasks lane, 58.5 to 44, with Supported evidence for both models, although the 90% intervals overlap.

Which costs less, Claude Sonnet 4.6 or GLM-5.2?

For the stated presets, chat costs $0.0105 on Claude Sonnet 4.6 and $0.0036 on GLM-5.2; repository review costs $0.195 and $0.0832; the cache-heavy agent loop costs $0.81 and $0.352. Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate. GLM-5.2 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Sonnet 4.6 or GLM-5.2?

GLM-5.2 has the larger documented context window: 1M, compared with 200K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 14, 2026

Watch Claude Sonnet 4.6 vs GLM-5.2

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.

Claude Sonnet 4.6 vs GLM-5.2

Which one for your work

Coding work

Agentic work

Long documents

Chat turn cost

Repository review cost

Cache-heavy agent loop cost

What is actually comparable

Category results, on a stated basis

Agentic

Coding

Knowledge

Instruction following

Reasoning

Math

Multilingual

Multimodal

Shape of the matched evidence

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

Benchmark evidence

Agentic

Coding

Reasoning

Knowledge

Math

Multimodal

Frequently asked questions

Which is better, Claude Sonnet 4.6 or GLM-5.2?

Which is better for coding, Claude Sonnet 4.6 or GLM-5.2?

Which is better for agentic tasks, Claude Sonnet 4.6 or GLM-5.2?

Which costs less, Claude Sonnet 4.6 or GLM-5.2?

Which has the larger context window, Claude Sonnet 4.6 or GLM-5.2?

Related comparisons

Watch Claude Sonnet 4.6 vs GLM-5.2